Transformations  in
Business & Economics

Support Vector Machines and their Application in Credit Risk Evaluation Process
Paulius Danenas, Gintautas Garsva

ABSTRACT. Support Vector Machines (SVM), like Neural Networks, is a method based on automatic learning from examples or machine learning, and is becoming very popular in researches as it gives promising opportunities in this field. This method has been developed with the means of adapting it for industrial applications and solutions and soon was applied in many statistical and intelligent fields, such as regression, time series analysis, pattern recognition systems and etc. It has been widely applied in different sciences, such as bioinformatics, text and document classification, pattern recognition, image recognition. One can also find a lot of examples of its application in finance and related sciences. The purpose of this article is to shortly describe the method itself, analyze current researches in credit risk evaluation and bankruptcy prediction and to discuss the further possibilities of its application in this field.

KEYWORDS: Support Vector Machines (SVM), artificial intelligence, machine learning, credit risk, evaluation, bankruptcy, forecasting, frameworks.

JEL classification: G17, G32, G33, C44, C45, C51, C52.